ai4bharat
/

hercule-bn

@@ -1,199 +1,100 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
 **BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+license: mit
+language:
+- bn
+metrics:
+- pearsonr
+- spearmanr
+- accuracy
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+pipeline_tag: text-generation
 ---
+# Model Card for Hercule
+Hercule is a cross-lingual evaluation model introduced as part of the CIA Suite to assess multilingual Large Language Models (LLMs). It addresses the challenge of evaluating multilingual LLMs by using English reference responses to score multilingual outputs.
+Fine-tuned on the INTEL dataset, Hercule demonstrates better alignment with human judgments compared to zero-shot evaluations by proprietary models like GPT-4, on the RECON test set. It excels particularly in low-resource scenarios and supports zero-shot evaluations on unseen languages. The model employs reference-based evaluation, providing feedback and scores on a 1-5 scale, and highlights the effectiveness of lightweight fine-tuning methods (like LoRA) for efficient multilingual evaluation. All FFT models and LoRA weights are available [here](https://huggingface.co/collections/ai4bharat/cia-suite-66ea9a7e18a6c70bd8de27a1).
+# Model Details
+## Model Description
+- **Model type:** Evaluator Language model
+- **Language(s) (NLP):** Bengali
+- **Related Models:** [Hercule Models](https://huggingface.co/collections/ai4bharat/cia-suite-66ea9a7e18a6c70bd8de27a1)
+- **Resources for more information:**
+  - [Research paper](https://arxiv.org/abs/2410.13394)
+  - [GitHub Repo](https://github.com/AI4Bharat/CIA)
+Hercule in fine-tuned on [Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) using Intel training data and evaluated on Recon test set. Models for other languages are available in [CIA Suite](https://huggingface.co/collections/ai4bharat/cia-suite-66ea9a7e18a6c70bd8de27a1).
+## Prompt Format
+We’ve developed wrapper functions and classes to make it easy to work with Hercule. Check them out on our [github repository](https://github.com/AI4Bharat/CIA) – we highly recommend using them!
+If you only need to use the model for your specific use case, please follow the prompt format provided below.
+### Reference Guided Direct Assessment
+The Hercule model expects four input components: an evaluation instruction (multilingual), a response to evaluate (multilingual), a scoring rubric (English), and a reference answer (English). Use the prompt format provided below, ensuring that you include the instruction, response, reference answer, evaluation criteria, and a detailed score rubric for each score from 1 to 5.
+After running inference with HERCULE, the output will include feedback and a score, separated by the phrase ```[RESULT]```.
+```
+###Task Description:
+An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
+1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
+2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
+3. The output format should look as follows: \"Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)\"
+4. Please do not generate any other opening, closing, and explanations.
+###The instruction to evaluate:
+{instruction}
+###Response to evaluate:
+{response}
+###Reference Answer (Score 5):
+{reference_answer}
+###Score Rubrics:
+[{criteria}]
+Score 1: {score1_rubric}
+Score 2: {score2_rubric}
+Score 3: {score3_rubric}
+Score 4: {score4_rubric}
+Score 5: {score5_rubric}
+###Feedback:
+```
+We use the same evaluation prompt as used in [Prometheus 2](https://huggingface.co/prometheus-eval/prometheus-7b-v2.0).
+## Links for Reference
+- **Repository**: https://github.com/AI4Bharat/CIA
+- **Paper**: https://arxiv.org/abs/2410.13394
+- **Point of Contact**: [email protected], [email protected]
+## License
+Intel training data is created from [Feedback Collection](https://huggingface.co/datasets/prometheus-eval/Feedback-Collection) which is subject to OpenAI's Terms of Use for the generated data. If you suspect any violations, please reach out to us.
+# Citation
+If you find the following model helpful, please consider citing our paper!
 **BibTeX:**
+```bibtex
+@misc{kim2023prometheus,
+    title={Sumanth Doddapaneni, Mohammed Safi Ur Rahman Khan, Dilip Venkatesh, Raj Dabre, Anoop Kunchukuttan, Mitesh M. Khapra},
+    year={2024},
+    eprint={2410.13394},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```